An adaptive communication scheme for bandwidth limited residential load forecasting

Guangrui Xie, Xi Chen, Yang Weng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While adding new capabilities, the distributed energy resource proliferation raises great concern about challenges such as dynamic fluctuations of voltages. For example, in a volatile setting with highly uncertain renewable generation and customer consumption, it is challenging to provide reliable power and voltage prediction for operational planning purposes to mitigate risks, e.g., over-voltages. In this paper, we propose an integrated Gaussian Process-based method (IGP) for electric load (consumption minus generation) prediction. For improving the forecasting accuracy, we use not only the data streams generated by the target customer but also those of relevant customers in the feeder system. An adaptive data communication rate controlling scheme is further proposed for dimension reduction of streaming data to address the situation when bandwidth limit enforces a constraint in some feeders. The goal is to make IGP with the same prediction precision but significantly less streaming data amount. The superior efficacy and efficiency of IGP and its enhanced variants are tested and verified on the standard IEEE 8-bus and 123-bus distribution test cases.

Original languageEnglish (US)
Title of host publication2017 North American Power Symposium, NAPS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538626993
DOIs
StatePublished - Nov 13 2017
Event2017 North American Power Symposium, NAPS 2017 - Morgantown, United States
Duration: Sep 17 2017Sep 19 2017

Other

Other2017 North American Power Symposium, NAPS 2017
CountryUnited States
CityMorgantown
Period9/17/179/19/17

Fingerprint

Load Forecasting
Integrated Process
Gaussian Process
Streaming Data
Customers
Voltage
Bandwidth
Prediction
Communication
Electric potential
Data Communication
Volatiles
Dimension Reduction
Proliferation
Data Streams
Electric loads
Forecasting
Efficacy
Energy resources
Planning

Keywords

  • active learning
  • Gaussian process
  • Load prediction

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Energy Engineering and Power Technology
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

Xie, G., Chen, X., & Weng, Y. (2017). An adaptive communication scheme for bandwidth limited residential load forecasting. In 2017 North American Power Symposium, NAPS 2017 [8107360] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NAPS.2017.8107360

An adaptive communication scheme for bandwidth limited residential load forecasting. / Xie, Guangrui; Chen, Xi; Weng, Yang.

2017 North American Power Symposium, NAPS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 8107360.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xie, G, Chen, X & Weng, Y 2017, An adaptive communication scheme for bandwidth limited residential load forecasting. in 2017 North American Power Symposium, NAPS 2017., 8107360, Institute of Electrical and Electronics Engineers Inc., 2017 North American Power Symposium, NAPS 2017, Morgantown, United States, 9/17/17. https://doi.org/10.1109/NAPS.2017.8107360
Xie G, Chen X, Weng Y. An adaptive communication scheme for bandwidth limited residential load forecasting. In 2017 North American Power Symposium, NAPS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 8107360 https://doi.org/10.1109/NAPS.2017.8107360
Xie, Guangrui ; Chen, Xi ; Weng, Yang. / An adaptive communication scheme for bandwidth limited residential load forecasting. 2017 North American Power Symposium, NAPS 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{9ea78f7d0bf7446d8948dbf67c835df2,
title = "An adaptive communication scheme for bandwidth limited residential load forecasting",
abstract = "While adding new capabilities, the distributed energy resource proliferation raises great concern about challenges such as dynamic fluctuations of voltages. For example, in a volatile setting with highly uncertain renewable generation and customer consumption, it is challenging to provide reliable power and voltage prediction for operational planning purposes to mitigate risks, e.g., over-voltages. In this paper, we propose an integrated Gaussian Process-based method (IGP) for electric load (consumption minus generation) prediction. For improving the forecasting accuracy, we use not only the data streams generated by the target customer but also those of relevant customers in the feeder system. An adaptive data communication rate controlling scheme is further proposed for dimension reduction of streaming data to address the situation when bandwidth limit enforces a constraint in some feeders. The goal is to make IGP with the same prediction precision but significantly less streaming data amount. The superior efficacy and efficiency of IGP and its enhanced variants are tested and verified on the standard IEEE 8-bus and 123-bus distribution test cases.",
keywords = "active learning, Gaussian process, Load prediction",
author = "Guangrui Xie and Xi Chen and Yang Weng",
year = "2017",
month = "11",
day = "13",
doi = "10.1109/NAPS.2017.8107360",
language = "English (US)",
booktitle = "2017 North American Power Symposium, NAPS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - An adaptive communication scheme for bandwidth limited residential load forecasting

AU - Xie, Guangrui

AU - Chen, Xi

AU - Weng, Yang

PY - 2017/11/13

Y1 - 2017/11/13

N2 - While adding new capabilities, the distributed energy resource proliferation raises great concern about challenges such as dynamic fluctuations of voltages. For example, in a volatile setting with highly uncertain renewable generation and customer consumption, it is challenging to provide reliable power and voltage prediction for operational planning purposes to mitigate risks, e.g., over-voltages. In this paper, we propose an integrated Gaussian Process-based method (IGP) for electric load (consumption minus generation) prediction. For improving the forecasting accuracy, we use not only the data streams generated by the target customer but also those of relevant customers in the feeder system. An adaptive data communication rate controlling scheme is further proposed for dimension reduction of streaming data to address the situation when bandwidth limit enforces a constraint in some feeders. The goal is to make IGP with the same prediction precision but significantly less streaming data amount. The superior efficacy and efficiency of IGP and its enhanced variants are tested and verified on the standard IEEE 8-bus and 123-bus distribution test cases.

AB - While adding new capabilities, the distributed energy resource proliferation raises great concern about challenges such as dynamic fluctuations of voltages. For example, in a volatile setting with highly uncertain renewable generation and customer consumption, it is challenging to provide reliable power and voltage prediction for operational planning purposes to mitigate risks, e.g., over-voltages. In this paper, we propose an integrated Gaussian Process-based method (IGP) for electric load (consumption minus generation) prediction. For improving the forecasting accuracy, we use not only the data streams generated by the target customer but also those of relevant customers in the feeder system. An adaptive data communication rate controlling scheme is further proposed for dimension reduction of streaming data to address the situation when bandwidth limit enforces a constraint in some feeders. The goal is to make IGP with the same prediction precision but significantly less streaming data amount. The superior efficacy and efficiency of IGP and its enhanced variants are tested and verified on the standard IEEE 8-bus and 123-bus distribution test cases.

KW - active learning

KW - Gaussian process

KW - Load prediction

UR - http://www.scopus.com/inward/record.url?scp=85040560749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040560749&partnerID=8YFLogxK

U2 - 10.1109/NAPS.2017.8107360

DO - 10.1109/NAPS.2017.8107360

M3 - Conference contribution

AN - SCOPUS:85040560749

BT - 2017 North American Power Symposium, NAPS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -